LangSmith Deployment

Start here if you’re building or operating agent applications. This section is about deploying your application. If you need to set up LangSmith infrastructure, the Hosting section covers infrastructure options (Cloud, Hybrid, Self-hosted) and setup guides for Hybrid and Self-hosted deployments.

This section covers how to package, build, and deploy your agents and applications as LangGraph Servers.

A typical deployment workflow consists of the following steps:

1. Test locally

   Run your application on a local server.

2. Configure app for deployment

   Set up dependencies, project structure, and environment configuration.

3. Choose hosting

   (Required for deployment) Select Cloud, Hybrid, or Self-hosted.

4. Deploy your app

   • Cloud: Push code from a git repository
   • Hybrid or Self-hosted with control plane: Build and push Docker images, deploy via UI
   • Standalone servers: Deploy directly without control plane
5. Monitor & manage

   Track traces, alerts, and dashboards.

What you’ll learn

• Configure your app for deployment (dependencies, project setup, and monorepo support).
• Build, deploy, and update LangGraph Servers.
• Secure your deployments with authentication and access control.
• Customize your server runtime (lifespan hooks, middleware, and routes).
• Debug, observe, and troubleshoot deployed agents using the Studio UI.

Get started with deployment

Package, build, and deploy your agents and graphs to LangGraph Server.

Configure your app

Related

• LangGraph Server
• Application structure
• Local server testing

---

Edit the source of this page on GitHub.

Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.